Akhilan Boopathy
9 papers · 2019–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (18) π Interdisciplinary Bridge π§ Keyword Pioneer π£ Hot Topic Early Bird π Conference Polyglot (4)
π
Academic Marathon
(6)
π
Cross-Pollinator
(11)
π
Conference Pioneer
π₯
Unstoppable
(7)
Conferences
ICML (5)
AAAI (2)
ICLR (1)
IJCAI (1)
Top co-authors
Keywords
adversarial robustness
(4)
neural network
(2)
inductive bia
(2)
information theory
(2)
robust optimization
(1)
robust classification
(1)
formal verification
(1)
gradient descent
(1)
adversarial attack
(1)
convolutional neural network
(1)
lower bound
(1)
neural network verification
(1)
neural network robustness
(1)
certified defense
(1)
robustness certificate
(1)
neural network certification
(1)
hypothesis space
(1)
network interpretability
(1)
perturbation bound
(1)
task complexity
(1)
Papers
Breaking Neural Network Scaling Laws with Modularity
ICLR 2025
Towards Exact Computation of Inductive Bias
IJCAI 2024
Rapid Learning without Catastrophic Forgetting in the Morris Water Maze
ICML 2024
Model-agnostic Measure of Generalization Difficulty
ICML 2023
How to Train Your Wide Neural Network Without Backprop: An Input-Weight Alignment Perspective
ICML 2022
Fast Training of Provably Robust Neural Networks by SingleProp
AAAI 2021
Proper Network Interpretability Helps Adversarial Robustness in Classification
ICML 2020
CNN-Cert: An Efficient Framework for Certifying Robustness of Convolutional Neural Networks
AAAI 2019
PROVEN: Verifying Robustness of Neural Networks with a Probabilistic Approach
ICML 2019